jishie

Qwen3.6 35B-A3B

alibaba/qwen3.6-35b-a3b · family qwen · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.

$0.84
Blended $/1M (3:1)
$0.375
Input $/1M
$2.25
Output $/1M
$2.63
1M in + 1M out
—
Cache read $/1M
#4037 of 8,504
Cheapest rank
Provider
Alibaba (alibaba)
Kind
text (outputs text)
Context
262,144 tokens
Max output
65,536 tokens
Capabilities
tools reasoning text image video

Same model, other providers

“Qwen3.6 35B-A3B” is offered by 24 providers — cheapest-effective first. NaN is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
NaNfreefree$0.00262k
QVACfreefree$0.00262k
engy$0.045$0.3$0.11208k
Boundless$0.04$0.35$0.12262k
SaladCloud AI Gateway$0.09$0.6$0.22262k
Zenifra$0.19$0.48$0.26262k
AKI.IO$0.1682$0.5608$0.27256k
Kilo Gateway$0.1$0.9$0.30262k
OpenRouter$0.1$0.9$0.30262k
Hugging Face$0.15$0.95$0.35262k
Ambient$0.15$1$0.36262k
DevPass (LLM Gateway)$0.248$1.49$0.56262k
Alibaba (this)$0.375$2.25$0.84262k

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Alibaba and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"qwen3.6-35b-a3b","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all Alibaba models · model index · JSON